Compute Capable Next-Generation Solid-State Drives (SSDs)

We are living in the data age. There is a growing interest for large scale data-intensive applications such as social networks, enterprise applications, scientific applications and data mining. Those applications are mainly limited by the poor performance of existing storage technologies (e.g., disks and flash). Emerging fast non-volatile memory (NVM) technologies appear as a boon to those applications. However, the existing solid-state drive (SSD) architecture and software optimize for flash and are not adequate to exploit the full potential of fast NVMs. It instigates a revolutionary change in existing SSD hardware and software. This book addresses those challenges and presents a novel SSD architecture called XSSD. XSSD offloads computation in storage to exploit fast NVMs and reduce the redundant data traffic across the I/O bus. XSSD offers a flexible RPC-based programming framework that developers can use for application development on SSD without dealing with the complication of the underlying architecture and communication management. XSSD achieves up to an order of performance improvement and energy efficiency as compared to the conventional I/O based SSD.

Autorentext

Arup De is graduated with PhD in Computer Science from the University of California, San Diego. His research interest is computer architecture, focusing on new system architectures for exploiting emerging technologies, designing scalable and efficient storage systems. During his PhD, he is a Lawrence Scholar at the Lawrence Livermore National Lab.